Update app.py

app.py

@@ -0,0 +1,216 @@
+import gradio as gr
+import pandas as pd
+from langchain.memory import VectorStoreRetrieverMemory
+from langchain_community.vectorstores import Chroma
+from langchain_openai import OpenAIEmbeddings, ChatOpenAI
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_core.prompts import PromptTemplate
+import chromadb
+import os
+from uuid import uuid4
+
+# Initialize persistent client
+CHROMA_PATH = "./vectordb-chroma/gformdb"
+os.makedirs(CHROMA_PATH, exist_ok=True)
+default_user_aspek = "Jika Jawaban salah berikan nilai 0, jika jawaban benar namun tidak tepat berikan nilai 50, jika jawaban benar dan lengkap serta penjelasan baik, beri nilai 100"
+
+def process_files(csv_file, openai_key, user_aspek=default_user_aspek, pdf_file=False, model_name="gpt-4o-mini"):
+    try:
+        context = ""
+
+        def context_search(query="a",source_name=False, k=5):
+
+            if source_name==True:
+                results = vectorstore.similarity_search(
+                    query=query,
+                    k=k,
+                    filter={"source": source_name}
+                )
+            else:
+                results = vectorstore.similarity_search(
+                    query=query,
+                    k=k,
+                )
+            for res in results:
+                page_content = res.page_content
+                metadata = res.metadata
+            return page_content, metadata
+
+        def format_qa_efficient(data_path):
+            data = pd.read_csv(data_path)
+            data.head()
+            qa_efficient = ""
+            indexs = 0
+            Question = ""
+            for column in data.columns[3:]:  # Lewati kolom Timestamp, Email Address, dan Nama
+                qa_efficient += f"Nomor-{indexs+1}.{column}:\n"
+                indexs += 1
+                Question += column
+                for index, row in data.iterrows():
+                    name = row['Nama']
+                    email = row["Email_Address"]
+                    answer = row[column]
+                    qa_efficient += f"- {name}|{email}: {answer}\n"
+                
+                qa_efficient += "\n"  # Baris kosong antara setiap pertanyaan
+
+            return qa_efficient, Question
+
+        # Set OpenAI API
+        if openai_key == "":
+            openai_key = os.getenv('OPENAI_API_KEY')
+            
+        os.environ["OPENAI_API_KEY"] = openai_key
+        
+        # Process CSV (Gradio provides the file path directly)
+
+        QA, Question = format_qa_efficient(csv_file)
+
+        if pdf_file:
+            # Initialize Chroma client
+            persistent_client = chromadb.PersistentClient(path=CHROMA_PATH)
+            collection = persistent_client.get_or_create_collection("RAG")
+            
+            vectorstore = Chroma(
+                client=persistent_client,
+                collection_name=collection.name,
+                embedding_function=OpenAIEmbeddings()
+            )
+            
+            res, metadata = context_search(pdf_file,k=1)
+
+            if metadata == pdf_file.name:
+                # Process PDF (Gradio provides the file path directly)
+                pages = PyPDFLoader(pdf_file.name).load_and_split()
+                uuids = [str(uuid4()) for _ in range(len(pages))]
+                vectorstore.add_documents(documents=pages, ids=uuids)
+            context, metadata = context_search(Question, pdf_file.name)
+
+        elif pdf_file == False:
+            context = "Tidak ada context tambahan yang diberikan, tolong gunakan pengetahuan anda untuk menjawab pertanyaan"
+        
+        # Evaluation template
+        TEMPLATE = """
+        Kamu adalah AI evaluator pendidikan. Nilai jawaban siswa berikut menggunakan panduan ini:
+
+        Buat output dengan format(format ini untuk satu murid, jadi selesaikan dulu 1 murid untuk semua nomor, baru ke murid berikutnya):
+        HASIL EVALUASI
+        =============
+        Nama dan Email Murid: 
+        [Nomor Soal].
+        Nilai: [Sesuaikan dengan Aspek Penilaian yang diberikan user]
+        Alasan: [alasan singkat penilaian]
+        Saran Perbaikan: [saran]
+
+        [buat seperti di atas untuk setiap jawaban]
+
+        ================
+        Rata-rata Nilai: [nilai]
+        
+        Rekomendasi Umum:
+        [rekomendasi]
+        
+
+        MATERI REFERENSI:
+        {context}   
+
+        SOAL & JAWABAN:
+        {QA}
+
+        Aspek Penilaian yang diberikan user:
+        {Aspek}
+
+
+        """
+        
+        PROMPT = PromptTemplate(
+            input_variables=["QA", "context", "Aspek"],
+            template=TEMPLATE
+        )
+        
+        # Initialize ChatGPT
+        chat = ChatOpenAI(model=model_name)
+        chain = PROMPT | chat
+        
+        # Generate evaluation
+        Aspek_penilaian = user_aspek
+        
+        response = chain.invoke({
+            "Aspek": Aspek_penilaian,
+            "QA": QA,
+            "context": context
+        })
+        
+        return response.content
+        
+    except Exception as e:
+        return f"Error occurred: {str(e)}\nType: {type(e)}"
+
+# Create Gradio interface
+def create_interface():
+    with gr.Blocks(title="Quiz Evaluator", theme=gr.themes.Soft()) as app:
+        with gr.Column(scale=1):
+            gr.Markdown(
+                """
+                # 📝 Quiz Response Evaluator
+                Upload your quiz responses (CSV) and reference material (PDF) to get AI-powered evaluation.
+                """
+            )
+            
+            with gr.Row():
+                with gr.Column(scale=1):
+                    csv_input = gr.File(
+                        label="Quiz Responses (CSV)",
+                        file_types=[".csv"]
+                    )
+                with gr.Column(scale=1):
+                    pdf_input = gr.File(
+                        label="Reference Material (PDF)",
+                        file_types=[".pdf"]
+                    )
+
+            user_aspek = gr.Textbox(
+                label="Aspek",
+                placeholder="Jika Jawaban salah berikan nilai 0, jika jawaban benar namun tidak tepat berikan nilai 50, jika jawaban benar dan lengkap serta penjelasan baik, beri nilai 100",
+                show_copy_button=True
+            )
+
+            model_name = gr.Textbox(
+                label="openAI model",
+                placeholder="input your openAI model",
+                value="gpt-4o-mini"
+            )
+            
+            api_key = gr.Textbox(
+                label="OpenAI API Key",
+                placeholder="Enter your OpenAI API key",
+                type="password"
+            )
+            
+            submit_btn = gr.Button(
+                "Evaluate Responses", 
+                variant="primary",
+                size="lg"
+            )
+            
+            # Using Textbox instead of Markdown for better formatting
+            output = gr.Textbox(
+                label="Evaluation Results",
+                lines=20,
+                max_lines=30,
+                show_copy_button=True
+            )
+
+        
+        submit_btn.click(
+            fn=process_files,
+            inputs=[csv_input,api_key,user_aspek,pdf_input,model_name],
+            outputs=output
+        )
+        
+    return app
+
+# Launch the interface
+if __name__ == "__main__":
+    app = create_interface()
+    app.launch(share=True)